Game-theoretic learning in a distributed-information setting: Distributed convergence to mean-centric equilibria

Brian Swenson; Soummya Kar; João Xavier

doi:10.1109/ACSSC.2014.7094739

Game-theoretic learning in a distributed-information setting: Distributed convergence to mean-centric equilibria

Brian Swenson
, Soummya Kar
, João Xavier

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The paper considers distributed learning in large-scale games via fictitious-play type algorithms. Given a preassigned communication graph structure for information exchange among the players, this paper studies a distributed implementation of the Empirical Centroid Fictitious Play (ECFP) algorithm that is well-suited to large-scale games in terms of complexity and memory requirements. It is shown that the distributed algorithm converges to an equilibrium set denoted as the mean-centric equilibria (MCE) for a reasonably large class of games.

Original language	English (US)
Title of host publication	Conference Record of the 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014
Editors	Michael B. Matthews
Publisher	IEEE Computer Society
Pages	1616-1620
Number of pages	5
ISBN (Electronic)	9781479982974
DOIs	https://doi.org/10.1109/ACSSC.2014.7094739
State	Published - Apr 24 2015
Event	48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014 - Pacific Grove, United States Duration: Nov 2 2014 → Nov 5 2014

Publication series

Name	Conference Record - Asilomar Conference on Signals, Systems and Computers
Volume	2015-April
ISSN (Print)	1058-6393
ISSN (Electronic)	2576-2303

Conference

Conference	48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014
Country/Territory	United States
City	Pacific Grove
Period	11/2/14 → 11/5/14

All Science Journal Classification (ASJC) codes

Signal Processing
Computer Networks and Communications

Access to Document

10.1109/ACSSC.2014.7094739

Cite this

Swenson, B., Kar, S., & Xavier, J. (2015). Game-theoretic learning in a distributed-information setting: Distributed convergence to mean-centric equilibria. In M. B. Matthews (Ed.), Conference Record of the 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014 (pp. 1616-1620). Article 7094739 (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2015-April). IEEE Computer Society. https://doi.org/10.1109/ACSSC.2014.7094739

Swenson, Brian ; Kar, Soummya ; Xavier, João. / Game-theoretic learning in a distributed-information setting : Distributed convergence to mean-centric equilibria. Conference Record of the 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014. editor / Michael B. Matthews. IEEE Computer Society, 2015. pp. 1616-1620 (Conference Record - Asilomar Conference on Signals, Systems and Computers).

@inproceedings{e775fe8d420542e8959aafade9be013c,

title = "Game-theoretic learning in a distributed-information setting: Distributed convergence to mean-centric equilibria",

abstract = "The paper considers distributed learning in large-scale games via fictitious-play type algorithms. Given a preassigned communication graph structure for information exchange among the players, this paper studies a distributed implementation of the Empirical Centroid Fictitious Play (ECFP) algorithm that is well-suited to large-scale games in terms of complexity and memory requirements. It is shown that the distributed algorithm converges to an equilibrium set denoted as the mean-centric equilibria (MCE) for a reasonably large class of games.",

author = "Brian Swenson and Soummya Kar and Jo{\~a}o Xavier",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014 ; Conference date: 02-11-2014 Through 05-11-2014",

year = "2015",

month = apr,

day = "24",

doi = "10.1109/ACSSC.2014.7094739",

language = "English (US)",

series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",

publisher = "IEEE Computer Society",

pages = "1616--1620",

editor = "Matthews, \{Michael B.\}",

booktitle = "Conference Record of the 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014",

address = "United States",

}

Swenson, B, Kar, S & Xavier, J 2015, Game-theoretic learning in a distributed-information setting: Distributed convergence to mean-centric equilibria. in MB Matthews (ed.), Conference Record of the 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014., 7094739, Conference Record - Asilomar Conference on Signals, Systems and Computers, vol. 2015-April, IEEE Computer Society, pp. 1616-1620, 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014, Pacific Grove, United States, 11/2/14. https://doi.org/10.1109/ACSSC.2014.7094739

Game-theoretic learning in a distributed-information setting: Distributed convergence to mean-centric equilibria. / Swenson, Brian; Kar, Soummya; Xavier, João.
Conference Record of the 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014. ed. / Michael B. Matthews. IEEE Computer Society, 2015. p. 1616-1620 7094739 (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2015-April).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Game-theoretic learning in a distributed-information setting

T2 - 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014

AU - Swenson, Brian

AU - Kar, Soummya

AU - Xavier, João

PY - 2015/4/24

Y1 - 2015/4/24

N2 - The paper considers distributed learning in large-scale games via fictitious-play type algorithms. Given a preassigned communication graph structure for information exchange among the players, this paper studies a distributed implementation of the Empirical Centroid Fictitious Play (ECFP) algorithm that is well-suited to large-scale games in terms of complexity and memory requirements. It is shown that the distributed algorithm converges to an equilibrium set denoted as the mean-centric equilibria (MCE) for a reasonably large class of games.

AB - The paper considers distributed learning in large-scale games via fictitious-play type algorithms. Given a preassigned communication graph structure for information exchange among the players, this paper studies a distributed implementation of the Empirical Centroid Fictitious Play (ECFP) algorithm that is well-suited to large-scale games in terms of complexity and memory requirements. It is shown that the distributed algorithm converges to an equilibrium set denoted as the mean-centric equilibria (MCE) for a reasonably large class of games.

UR - https://www.scopus.com/pages/publications/84940540105

UR - https://www.scopus.com/pages/publications/84940540105#tab=citedBy

U2 - 10.1109/ACSSC.2014.7094739

DO - 10.1109/ACSSC.2014.7094739

M3 - Conference contribution

AN - SCOPUS:84940540105

T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers

SP - 1616

EP - 1620

BT - Conference Record of the 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014

A2 - Matthews, Michael B.

PB - IEEE Computer Society

Y2 - 2 November 2014 through 5 November 2014

ER -

Swenson B, Kar S, Xavier J. Game-theoretic learning in a distributed-information setting: Distributed convergence to mean-centric equilibria. In Matthews MB, editor, Conference Record of the 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014. IEEE Computer Society. 2015. p. 1616-1620. 7094739. (Conference Record - Asilomar Conference on Signals, Systems and Computers). doi: 10.1109/ACSSC.2014.7094739

Game-theoretic learning in a distributed-information setting: Distributed convergence to mean-centric equilibria

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this